Merge branch 'main' into pr/296

apps/api/src/services/rate-limiter.test.ts

@@ -0,0 +1,87 @@
+import { getRateLimiter, serverRateLimiter, testSuiteRateLimiter, redisClient } from "./rate-limiter";
+import { RateLimiterMode } from "../../src/types";
+import { RateLimiterRedis } from "rate-limiter-flexible";
+
+describe("Rate Limiter Service", () => {
+  beforeAll(async () => {
+    await redisClient.connect();
+  });
+
+  afterAll(async () => {
+    await redisClient.disconnect();
+  });
+
+  it("should return the testSuiteRateLimiter for specific tokens", () => {
+    const limiter = getRateLimiter("crawl" as RateLimiterMode, "a01ccae");
+    expect(limiter).toBe(testSuiteRateLimiter);
+
+    const limiter2 = getRateLimiter("scrape" as RateLimiterMode, "6254cf9");
+    expect(limiter2).toBe(testSuiteRateLimiter);
+  });
+
+  it("should return the serverRateLimiter if mode is not found", () => {
+    const limiter = getRateLimiter("nonexistent" as RateLimiterMode, "someToken");
+    expect(limiter).toBe(serverRateLimiter);
+  });
+
+  it("should return the correct rate limiter based on mode and plan", () => {
+    const limiter = getRateLimiter("crawl" as RateLimiterMode, "someToken", "free");
+    expect(limiter.points).toBe(2);
+
+    const limiter2 = getRateLimiter("scrape" as RateLimiterMode, "someToken", "standard");
+    expect(limiter2.points).toBe(50);
+
+    const limiter3 = getRateLimiter("search" as RateLimiterMode, "someToken", "growth");
+    expect(limiter3.points).toBe(500);
+
+    const limiter4 = getRateLimiter("crawlStatus" as RateLimiterMode, "someToken", "growth");
+    expect(limiter4.points).toBe(150);
+  });
+
+  it("should return the default rate limiter if plan is not provided", () => {
+    const limiter = getRateLimiter("crawl" as RateLimiterMode, "someToken");
+    expect(limiter.points).toBe(3);
+
+    const limiter2 = getRateLimiter("scrape" as RateLimiterMode, "someToken");
+    expect(limiter2.points).toBe(20);
+  });
+
+  it("should create a new RateLimiterRedis instance with correct parameters", () => {
+    const keyPrefix = "test-prefix";
+    const points = 10;
+    const limiter = new RateLimiterRedis({
+      storeClient: redisClient,
+      keyPrefix,
+      points,
+      duration: 60,
+    });
+
+    expect(limiter.keyPrefix).toBe(keyPrefix);
+    expect(limiter.points).toBe(points);
+    expect(limiter.duration).toBe(60);
+  });
+
+  it("should return the correct rate limiter for 'preview' mode", () => {
+    const limiter = getRateLimiter("preview" as RateLimiterMode, "someToken", "free");
+    expect(limiter.points).toBe(5);
+
+    const limiter2 = getRateLimiter("preview" as RateLimiterMode, "someToken");
+    expect(limiter2.points).toBe(5);
+  });
+
+  it("should return the correct rate limiter for 'account' mode", () => {
+    const limiter = getRateLimiter("account" as RateLimiterMode, "someToken", "free");
+    expect(limiter.points).toBe(100);
+
+    const limiter2 = getRateLimiter("account" as RateLimiterMode, "someToken");
+    expect(limiter2.points).toBe(100);
+  });
+
+  it("should return the correct rate limiter for 'crawlStatus' mode", () => {
+    const limiter = getRateLimiter("crawlStatus" as RateLimiterMode, "someToken", "free");
+    expect(limiter.points).toBe(150);
+
+    const limiter2 = getRateLimiter("crawlStatus" as RateLimiterMode, "someToken");
+    expect(limiter2.points).toBe(150);
+  });
+});

apps/js-sdk/example.ts

@@ -1,11 +1,14 @@
-import FirecrawlApp, { JobStatusResponse } from '@mendable/firecrawl-js';
+import FirecrawlApp, { JobStatusResponse } from './firecrawl/src/index' //'@mendable/firecrawl-js';
 import { z } from "zod";
 
 const app = new FirecrawlApp({apiKey: "fc-YOUR_API_KEY"});
 
 // Scrape a website:
 const scrapeResult = await app.scrapeUrl('firecrawl.dev');
-console.log(scrapeResult.data.content)
+
+if (scrapeResult.data) {
+  console.log(scrapeResult.data.content)
+}
 
 // Crawl a website:
 const crawlResult = await app.crawlUrl('mendable.ai', {crawlerOptions: {excludes: ['blog/*'], limit: 5}}, false);
@@ -23,12 +26,13 @@ while (true) {
   await new Promise(resolve => setTimeout(resolve, 1000)); // wait 1 second
 }
 
-console.log(job.data[0].content);
+if (job.data) {
+  console.log(job.data[0].content);
+}
 
 // Search for a query:
 const query = 'what is mendable?'
 const searchResult = await app.search(query)
-console.log(searchResult)
 
 // LLM Extraction:
 //  Define schema to extract contents into using zod schema
@@ -50,7 +54,9 @@ let llmExtractionResult = await app.scrapeUrl("https://news.ycombinator.com", {
   extractorOptions: { extractionSchema: zodSchema },
 });
 
-console.log(llmExtractionResult.data.llm_extraction);
+if (llmExtractionResult.data) {
+  console.log(llmExtractionResult.data.llm_extraction);
+}
 
 // Define schema to extract contents into using json schema
 const jsonSchema = {
@@ -80,4 +86,7 @@ llmExtractionResult = await app.scrapeUrl("https://news.ycombinator.com", {
   extractorOptions: { extractionSchema: jsonSchema },
 });
 
-console.log(llmExtractionResult.data.llm_extraction);
+if (llmExtractionResult.data) {
+  console.log(llmExtractionResult.data.llm_extraction);
+}
+

apps/js-sdk/firecrawl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mendable/firecrawl-js",
-  "version": "0.0.26",
+  "version": "0.0.27",
   "description": "JavaScript SDK for Firecrawl API",
   "main": "build/index.js",
   "types": "types/index.d.ts",

apps/js-sdk/firecrawl/src/index.ts

@@ -5,61 +5,117 @@ import { zodToJsonSchema } from "zod-to-json-schema";
  * Configuration interface for FirecrawlApp.
  */
 export interface FirecrawlAppConfig {
-    apiKey?: string | null;
-    apiUrl?: string | null;
+  apiKey?: string | null;
+  apiUrl?: string | null;
 }
 
 /**
- * Generic parameter interface.
+ * Metadata for a Firecrawl document.
  */
-export interface Params {
-    [key: string]: any;
-    extractorOptions?: {
-        extractionSchema: z.ZodSchema | any;
-        mode?: "llm-extraction";
-        extractionPrompt?: string;
-    };
+export interface FirecrawlDocumentMetadata {
+  title?: string;
+  description?: string;
+  language?: string;
+  keywords?: string;
+  robots?: string;
+  ogTitle?: string;
+  ogDescription?: string;
+  ogUrl?: string;
+  ogImage?: string;
+  ogAudio?: string;
+  ogDeterminer?: string;
+  ogLocale?: string;
+  ogLocaleAlternate?: string[];
+  ogSiteName?: string;
+  ogVideo?: string;
+  dctermsCreated?: string;
+  dcDateCreated?: string;
+  dcDate?: string;
+  dctermsType?: string;
+  dcType?: string;
+  dctermsAudience?: string;
+  dctermsSubject?: string;
+  dcSubject?: string;
+  dcDescription?: string;
+  dctermsKeywords?: string;
+  modifiedTime?: string;
+  publishedTime?: string;
+  articleTag?: string;
+  articleSection?: string;
+  sourceURL?: string;
+  pageStatusCode?: number;
+  pageError?: string;
+  [key: string]: any;
+}
+
+/**
+ * Document interface for Firecrawl.
+ */
+export interface FirecrawlDocument {
+  id?: string;
+  url?: string;
+  content: string;
+  markdown?: string;
+  html?: string;
+  llm_extraction?: Record<string, any>;
+  createdAt?: Date;
+  updatedAt?: Date;
+  type?: string;
+  metadata: FirecrawlDocumentMetadata;
+  childrenLinks?: string[];
+  provider?: string;
+  warning?: string;
+
+  index?: number;
 }
 
 /**
  * Response interface for scraping operations.
  */
 export interface ScrapeResponse {
-    success: boolean;
-    data?: any;
-    error?: string;
+   success: boolean;
+   data?: FirecrawlDocument;
+   error?: string;
 }
-
 /**
- * Response interface for searching operations.
- */
+* Response interface for searching operations.
+*/
 export interface SearchResponse {
-    success: boolean;
-    data?: any;
-    error?: string;
+   success: boolean;
+   data?: FirecrawlDocument[];
+   error?: string;
 }
 /**
- * Response interface for crawling operations.
- */
+* Response interface for crawling operations.
+*/
 export interface CrawlResponse {
-    success: boolean;
-    jobId?: string;
-    data?: any;
-    error?: string;
+   success: boolean;
+   jobId?: string;
+   data?: FirecrawlDocument[];
+   error?: string;
 }
-
 /**
- * Response interface for job status checks.
- */
+* Response interface for job status checks.
+*/
 export interface JobStatusResponse {
-    success: boolean;
-    status: string;
-    jobId?: string;
-    data?: any;
-    partial_data?: any,
-    error?: string;
+   success: boolean;
+   status: string;
+   jobId?: string;
+   data?: FirecrawlDocument[];
+   partial_data?: FirecrawlDocument[];
+   error?: string;
+}
+/**
+  * Generic parameter interface.
+  */
+export interface Params {
+   [key: string]: any;
+   extractorOptions?: {
+       extractionSchema: z.ZodSchema | any;
+       mode?: "llm-extraction";
+       extractionPrompt?: string;
+   };
 }
-
 /**
  * Main class for interacting with the Firecrawl API.
  */

apps/js-sdk/firecrawl/types/index.d.ts

@@ -8,8 +8,101 @@ export interface FirecrawlAppConfig {
     apiUrl?: string | null;
 }
 /**
- * Generic parameter interface.
+ * Metadata for a Firecrawl document.
  */
+export interface FirecrawlDocumentMetadata {
+    title?: string;
+    description?: string;
+    language?: string;
+    keywords?: string;
+    robots?: string;
+    ogTitle?: string;
+    ogDescription?: string;
+    ogUrl?: string;
+    ogImage?: string;
+    ogAudio?: string;
+    ogDeterminer?: string;
+    ogLocale?: string;
+    ogLocaleAlternate?: string[];
+    ogSiteName?: string;
+    ogVideo?: string;
+    dctermsCreated?: string;
+    dcDateCreated?: string;
+    dcDate?: string;
+    dctermsType?: string;
+    dcType?: string;
+    dctermsAudience?: string;
+    dctermsSubject?: string;
+    dcSubject?: string;
+    dcDescription?: string;
+    dctermsKeywords?: string;
+    modifiedTime?: string;
+    publishedTime?: string;
+    articleTag?: string;
+    articleSection?: string;
+    sourceURL?: string;
+    pageStatusCode?: number;
+    pageError?: string;
+    [key: string]: any;
+}
+/**
+ * Document interface for Firecrawl.
+ */
+export interface FirecrawlDocument {
+    id?: string;
+    url?: string;
+    content: string;
+    markdown?: string;
+    html?: string;
+    llm_extraction?: Record<string, any>;
+    createdAt?: Date;
+    updatedAt?: Date;
+    type?: string;
+    metadata: FirecrawlDocumentMetadata;
+    childrenLinks?: string[];
+    provider?: string;
+    warning?: string;
+    index?: number;
+}
+/**
+ * Response interface for scraping operations.
+ */
+export interface ScrapeResponse {
+    success: boolean;
+    data?: FirecrawlDocument;
+    error?: string;
+}
+/**
+* Response interface for searching operations.
+*/
+export interface SearchResponse {
+    success: boolean;
+    data?: FirecrawlDocument[];
+    error?: string;
+}
+/**
+* Response interface for crawling operations.
+*/
+export interface CrawlResponse {
+    success: boolean;
+    jobId?: string;
+    data?: FirecrawlDocument[];
+    error?: string;
+}
+/**
+* Response interface for job status checks.
+*/
+export interface JobStatusResponse {
+    success: boolean;
+    status: string;
+    jobId?: string;
+    data?: FirecrawlDocument[];
+    partial_data?: FirecrawlDocument[];
+    error?: string;
+}
+/**
+  * Generic parameter interface.
+  */
 export interface Params {
     [key: string]: any;
     extractorOptions?: {
@@ -18,42 +111,6 @@ export interface Params {
         extractionPrompt?: string;
     };
 }
-/**
- * Response interface for scraping operations.
- */
-export interface ScrapeResponse {
-    success: boolean;
-    data?: any;
-    error?: string;
-}
-/**
- * Response interface for searching operations.
- */
-export interface SearchResponse {
-    success: boolean;
-    data?: any;
-    error?: string;
-}
-/**
- * Response interface for crawling operations.
- */
-export interface CrawlResponse {
-    success: boolean;
-    jobId?: string;
-    data?: any;
-    error?: string;
-}
-/**
- * Response interface for job status checks.
- */
-export interface JobStatusResponse {
-    success: boolean;
-    status: string;
-    jobId?: string;
-    data?: any;
-    partial_data?: any;
-    error?: string;
-}
 /**
  * Main class for interacting with the Firecrawl API.
  */